Skip to content
🎯
Focusing
🎯
Focusing
Pro
Block or report user

Report or block jiesutd

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse

Organizations

@SUTDNLP
Block or report user

Report or block jiesutd

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse

Pinned

  1. NCRF++, an Open-source Neural Sequence Labeling Toolkit. It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components. (code for COLING/ACL 2018 paper)

    Python 1.3k 327

  2. YEDDA: A Lightweight Collaborative Text Span Annotation Tool. Code for ACL 2018 Best Demo Paper Nomination.

    Python 445 149

  3. Neural word segmentation with rich pretraining, code for ACL 2017 paper

    C++ 99 22

  4. Chinese NER using Lattice LSTM. Code for ACL 2018 paper.

    Python 832 268

  5. LibN3L: A light-weight neural network package for natural language

    C++ 75 31

  6. Plot the vector graph of attention based text visualisation

    Python 53 8

1 contribution in the last year in LancoPKU

Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Mon Wed Fri
Activity in LancoPKU
Contributed to pkuseg-python
Loading

Contribution activity in LancoPKU

February - September 2019

jiesutd has no activity in LancoPKU yet for this period.

January 2019

Created an issue in lancopku/pkuseg-python that received 31 comments

与其余分词工具包的性能对比并不公平吧?

请问一下对比的jieba 和 THULAC 模型有用对应的训练语料(MSRA,CTB8)训练么? 如果有训练语料的话,这两个模型的结果应该不会那么差。80%左右的F值都快和unsupervised segmentation 差不多了。 如果用in domain 训练语料训练的pkuseg 和 …

31 comments

Seeing something unexpected? Take a look at the GitHub profile guide.

You can’t perform that action at this time.